Loomcycle spawn evaluator

Spawn a loomcycle evaluator

Use this when the operator wants an independent evaluation of work — either the current Claude Code transcript or a specific loomcycle run — scored by a loomcycle evaluator agent rather than by you directly.

Steps:

1. Identify what's being evaluated. Ask the operator (or infer) whether they want to evaluate (a) the work in the current conversation, or (b) a specific completed run. If (b), get the run_id.

2. Choose the evaluator agent. Ask which registered loomcycle agent should act as evaluator (e.g. evaluator, judge). Do not guess a name — if none is known, list options via the runs/agents the operator mentions, or ask.

3. Spawn the evaluator with mcp__loomcycle__spawn_run. Pass the material to be judged as the prompt, wrapped as segments:

   {
     "agent": "<evaluator-agent>",
     "segments": [
       { "role": "user", "content": [
         { "type": "trusted-text", "text": "Evaluate the following and return a score 0-1 with a one-line rationale:\n\n<material>" }
       ] }
     ]
   }
   

   Use the active user_id / user_bearer from /loomcycle:connect if set.

4. Report the evaluator's score + rationale back to the operator clearly.

5. Offer to record it. If the work corresponds to a real run_id, offer to submit the score via /loomcycle:eval <run_id> <score>. loomcycle does not auto-promote on scores — recording is the operator's call.

Keep the loop honest: you are orchestrating an independent judge, so don't pre-bias the evaluator's prompt toward a verdict.